© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18255
    Prev
    Next
    INDEX
    Explanations

    additional, extra, second, third

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç°Į
    -0.10
    å¤Ħå¤Ħ
    -0.10
    åIJİåı°
    -0.09
    åħ±åĴĮåĽ½
    -0.09
    åĶ§
    -0.09
    inan
    -0.08
    à¸Īำà¸ģ
    -0.08
     ë¬
    -0.08
    é«ij
    -0.08
    ikon
    -0.08
    POSITIVE LOGITS
    é¢Ŀå¤ĸ
    0.15
    additional
    0.14
     additional
    0.14
    第ä¸ī个
    0.12
     Additional
    0.12
    Additional
    0.12
     дополн
    0.11
    (extra
    0.11
    _additional
    0.11
     added
    0.11
    Activations Density 0.314%

    No Known Activations